{"id":13444353,"url":"https://github.com/polarisZhao/awesome-face","last_synced_at":"2025-03-20T18:32:02.805Z","repository":{"id":111764091,"uuid":"133211470","full_name":"polarisZhao/awesome-face","owner":"polarisZhao","description":"😎 face releated algorithm, dataset and paper ","archived":false,"fork":false,"pushed_at":"2019-08-27T15:13:39.000Z","size":2491,"stargazers_count":882,"open_issues_count":3,"forks_count":182,"subscribers_count":46,"default_branch":"master","last_synced_at":"2024-05-23T06:27:03.175Z","etag":null,"topics":["dataset","face","face-detection","face-recognition","face-releated-algorithm","paper","papers"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/polarisZhao.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-05-13T06:23:30.000Z","updated_at":"2024-04-25T22:20:38.000Z","dependencies_parsed_at":"2023-07-24T17:15:55.542Z","dependency_job_id":null,"html_url":"https://github.com/polarisZhao/awesome-face","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/polarisZhao%2Fawesome-face","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/polarisZhao%2Fawesome-face/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/polarisZhao%2Fawesome-face/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/polarisZhao%2Fawesome-face/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/polarisZhao","download_url":"https://codeload.github.com/polarisZhao/awesome-face/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244670406,"owners_count":20490971,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataset","face","face-detection","face-recognition","face-releated-algorithm","paper","papers"],"created_at":"2024-07-31T04:00:20.597Z","updated_at":"2025-03-20T18:32:02.296Z","avatar_url":"https://github.com/polarisZhao.png","language":null,"funding_links":[],"categories":["Uncategorized","Awesome Lists","Table of Contents","Others","Awesome \"awesome-\"","Summary","Other Lists"],"sub_categories":["Uncategorized","TeX Lists"],"readme":"# awesome-face [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/polarisZhao/awesome-face)\n🔥  face releated algorithm, datasets and papers   \n\n\u003c!--ts--\u003e\n\n* [ Paper / Algorithm](#-paper--algorithm)\n  - [Survey](#Survey)\n  - [2D- Face Recognition](#2d--face-recognition)\n  - [Face Detection](#face-detection)\n  - [Face Alignment](#face-alignment)\n  - [3D face reconstruction](#3D-face-reconstruction)\n  - [Face attack \u0026amp; Defends](#face-attack--defends)\n  \n* [Open source lib](#-open-source-lib) \n  - [face recognition](#face-recognition)\n  -  [face detection](#face-detection-1)\n\n* [Datasets](#-datasets)\n  \n  - [2D Face Recognition](#2d-face-recognition) \n  - [video face recognition](#video-face-recognition) \n  - [3D face recognition](#3d-face-recognition)\n  - [Anti-spoofing](#anti-spoofing)\n  - [cross age and cross pose](#cross-age-and-cross-pose)\n  -  [Face Detection](#face-detection-2)\n  -  [Face Attributes](#face-attributes)\n-  [Others](#others)\n  \n* [ Research home(conf \u0026amp; workshop \u0026amp; trans)](#-research-homeconf--workshop--trans)\n\n* [ References:](#-references)\n\n\u003c!--te--\u003e\n\n## 📝 Paper / Algorithm\n\n#### Survey\n\n- Deep Face Recognition: A Survey  [paper](https://arxiv.org/abs/1804.06655)\n- Face Recognition: From Traditional to Deep Learning Methods  [paper](https://arxiv.org/abs/1811.00116)\n- Deep Facial Expression Recognition: A Survey  [paper](https://arxiv.org/abs/1804.08348)\n- A Survey on Face Detection and Classification for Partially Occluded images [paper](http://ijariie.com/AdminUploadPdf/A_Survey_on_Face_Detection_and_Classification_for_Partially_Occluded_images_ijariie9406.pdf)\n- 3D face recognition: a survey  [paper](https://link.springer.com/article/10.1186/s13673-018-0157-2)\n- Face detection techniques: a review [paper](https://link.springer.com/article/10.1007/s10462-018-9650-2)\n\n#### 2D- Face Recognition \n\n![2d_face_reg](./img/face_reg.jpg)\n\n**[1] DeepID1**  [**[paper]**](https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Sun_Deep_Learning_Face_2014_CVPR_paper.pdf) \n\nDeep Learning Face Representation from Predicting 10,000 Classes\n\n**[2] DeepID2**  [**[paper]**](https://arxiv.org/abs/1406.4773) \n\nDeep Learning Face Representation by Joint Identification-Verification\n\n**[3] DeepID2+**  [**[paper]**](https://arxiv.org/abs/1412.1265)\n\nDeeply learned face representations are sparse, selective, and robust\n\n**[4] DeepIDv3**  [**[paper]**](https://arxiv.org/abs/1502.00873) \n\nDeepID3: Face Recognition with Very Deep Neural Networks\n\n**[5] Deep Face** [**[paper]**](https://www.cs.toronto.edu/~ranzato/publications/taigman_cvpr14.pdf) \n\nDeep Face Recognition\n\n**[6] Center Loss** [**[paper]**](http://ydwen.github.io/papers/WenECCV16.pdf)    [**[code]**](https://github.com/ydwen/caffe-face)\n\nA Discriminative Feature Learning Approach for Deep Face Recognition\n\n**[7]Marginal loss** [**[paper]**](https://www.computer.org/csdl/proceedings-article/cvprw/2017/0733c006/12OmNzayNCT)\n\nMarginal loss for deep face recognition\n\n**[8] Range Loss**[**[paper]**](https://arxiv.org/abs/1611.08976) \n\nRange Loss for Deep Face Recognition with Long-tail\n\n**[9]Contrastive Loss** [**[paper]**](\u003chttps://arxiv.org/abs/1406.4773\u003e)\n\nDeep learning face representation by joint identification-verification\n\n**[10] FaceNet**   [**[paper]**](https://arxiv.org/abs/1503.03832)   [[**third-party implemention**]](https://github.com/davidsandberg/facenet)\n\nFaceNet: A Unified Embedding for Face Recognition and Clustering\n\n**[11] NormFace**  [**[paper]**](https://arxiv.org/pdf/1704.06369.pdf)    [**[code]**](https://github.com/happynear/NormFace)\n\nNormFace: L2 Hypersphere Embedding for Face Verification\n\n**[12] COCO Loss:**    [**[paper]**](https://arxiv.org/pdf/1710.00870.pdf)   [[**code**]](https://github.com/sciencefans/coco_loss)\n\nRethinking Feature Discrimination and Polymerization for Large-scale Recognition\n\n**[13] Large-Margin Softmax Loss**  [**[paper]**](https://arxiv.org/pdf/1612.02295.pdf)  [[**code**]](https://github.com/wy1iu/LargeMargin_Softmax_Loss)\n\nLarge-Margin Softmax Loss for Convolutional Neural Networks(L-Softmax loss)\n\n**[14]SphereFace：**  **A-Softmax**   [**[paper]**](https://arxiv.org/abs/1704.08063)  [[**code**]](https://github.com/wy1iu/sphereface)\n\nSphereFace: Deep Hypersphere Embedding for Face Recognition\n\n**[15]AM-Softmax/cosFace**     [**[paper AM-Softmax]**](https://arxiv.org/pdf/1801.05599.pdf)       [**[paper cosFace]**](https://arxiv.org/pdf/1801.09414.pdf)        [[**AM-softmax code**]](https://github.com/happynear/AMSoftmax)\n\nAM : Additive Margin Softmax for Face Verification\n\nCosFace: Large Margin Cosine Loss for Deep Face Recognition(Tencent AI Lab)\n\n**[16] ArcFace:**  [**[paper]**](https://arxiv.org/pdf/1801.07698.pdf)  [**[code]**](https://github.com/deepinsight/insightface )\n\nArcFace: Additive Angular Margin Loss for Deep Face Recognition\n\n**[17] Adaptive Face**    [paper](http://www.cbsr.ia.ac.cn/users/xiangyuzhu/papers/2019adaptiveface.pdf)\n\nAdaptive Margin and Sampling for Face Recognition\n\n**[18] AdaCos**   [Paper](https://arxiv.org/abs/1905.00292)\n\n Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations\n\n**[20] RegularFace**: [paper](http://mftp.mmcheng.net/Papers/19cvprRegularFace.pdf)\n\nDeep Face Recognition via Exclusive Regularization\n\n**[21] UniformFace**:  [paper](http://ivg.au.tsinghua.edu.cn/people/Yueqi_Duan/CVPR19_UniformFace%20Learning%20Deep%20Equidistributed%20Representation%20for%20Face%20Recognition.pdf)\n\nLearning Deep Equidistributed Representation for Face Recognition\n\n**[22] P2SGrad**:  [paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_P2SGrad_Refined_Gradients_for_Optimizing_Deep_Face_Models_CVPR_2019_paper.pdf)\n\nRefined Gradients for Optimizing Deep Face Models\n\n![cos_loss](./img/cos_loss.jpg)\n\n#### Face Detection\n\n![](./img/face_detection.jpg)\n\n**[1] Cascade CNN**  [**[paper]**](https://ieeexplore.ieee.org/document/7299170/) [**[code]**](https://github.com/anson0910/CNN_face_detection)    \n\nA Convolutional Neural Network Cascade for Face Detection\n\n**[2] MTCNN**   [**[Paper]**](https://kpzhang93.github.io/MTCNN_face_detection_alignment/)    [**[code]**](https://github.com/kpzhang93/MTCNN_face_detection_alignment)  \n\nJoint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks\n\n**[3] ICC - CNN**  [**[paper]**](https://ieeexplore.ieee.org/document/8237606)\n\nDetecting Faces Using Inside Cascaded Contextual CNN\n\n**[4] Face R-CNN**  [**[Paper]**](https://arxiv.org/pdf/1706.01061.pdf)\n\nFace R-CNN\n\n**[5] Deep-IR**[**[Paper]**](https://arxiv.org/abs/1701.08289)\n\nFace Detection using Deep Learning: An Improved Faster RCNN Approach\n\n**[6] SSH**     [**[paper]**](https://arxiv.org/pdf/1708.03979.pdf)    [**[code]**](https://github.com/mahyarnajibi/SSH)\n\nSSH: Single Stage Headless Face Detector\n\n**[7] S3FD**   [**[paper]**](https://arxiv.org/abs/1708.05237)\n\nSingle Shot Scale-invariant Face Detector\n\n**[8] FaceBoxes** [**[paper]**](https://arxiv.org/pdf/1708.05234.pdf)     [**[code]**](https://github.com/sfzhang15/FaceBoxes)\n\nFaceboxes: A CPU Real-time Face Detector with High Accuracy\n\n**[9] Scaleface**     [**[paper]**](http://cn.arxiv.org/abs/1706.02863)\n\nFace Detection through Scale-Friendly Deep Convolutional Networks\n\n**[10] HR**  [**[paper]**](https://arxiv.org/abs/1612.04402)  [**[code]**](https://github.com/peiyunh/tiny)\n\nFinding Tiny Faces\n\n**[11] FAN**   [**[paper]**](https://arxiv.org/abs/1712.00721)\n\nFeature Agglomeration Networks for Single Stage Face Detection.\n\n**[12] PyramidBox**    [**[paper]**](https://arxiv.org/abs/1803.07737?context=cs) [**[code]**](https://github.com/PaddlePaddle/models/blob/develop/fluid/PaddleCV/face_detection/README_cn.md)\n\nPyramidBox: A Context-assisted Single Shot Face Detector\n\n**[13] SRN**     [**[paper]**](https://arxiv.org/abs/1809.02693) \n\nSelective Refinement Network for High Performance Face Detection.\n\n**[14] DSFD**  [**[paper]**](https://arxiv.org/abs/1810.10220)\n\nDSFD: Dual Shot Face Detector\n\n**[15] VIM FD** [**[paper]**](https://arxiv.org/abs/1901.02350)\n\nRobust and High Performance Face Detector\n\n**[16] ISRN**  [**[paper]**](https://arxiv.org/abs/1901.06651)\n\nImproved Selective Refinement Network for Face Detection\n\n**[17] PyramidBox++**  [**[Paper]**](https://arxiv.org/abs/1904.00386)\n\nPyramidBox++: High Performance Detector for Finding Tiny Face\n\n**[18] RetinaFace**    [**[paper]**](https://arxiv.org/pdf/1905.00641.pdf)  [**[code]**](https://github.com/deepinsight/insightface/tree/master/RetinaFace)\n\nRetinaFace: Single-stage Dense Face Localisation in the Wild\n\n#### Face Alignment\n\n**[1] PRNet**     [**[paper]**](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yao_Feng_Joint_3D_Face_ECCV_2018_paper.pdf)  [**[code]**](https://github.com/YadiraF/PRNet)  \n\nJoint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network\n\n**[2]LAB**   [Paper](https://arxiv.org/abs/1805.10483)    [**[code]**](https://github.com/wywu/LAB)\n\nLook at Boundary: A Boundary-Aware Face Alignment Algorithm\n\n**[3]PFLD**   [Paper](https://arxiv.org/pdf/1902.10859.pdf)    [**[demo code]**](https://sites.google.com/view/xjguo/fld)\n\nPFLD: A Practical Facial Landmark Detector\n\n**[4] 2D \u0026 3D FAN**   [**[Paper]**](https://www.adrianbulat.com/downloads/FaceAlignment/FaceAlignment.pdf)    [**[code]**](https://github.com/1adrianb/face-alignment)\n\nHow far are we from solving the 2D \u0026 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)\n\n#### 3D face reconstruction\n\n**[1] 3DMM** \n\nA Morphable Model For The Synthesis Of 3D Faces\n\n**[2] 3DDFA**      [**[paper]**](https://arxiv.org/abs/1804.01005)     [**[github]**](https://github.com/cleardusk/3DDFA)\n\nFace Alignment in Full Pose Range: A 3D Total Solution.\n\n**[3] VRN**       [**[index]**](http://aaronsplace.co.uk/papers/jackson2017recon/index.html)    [**[code]**](https://github.com/AaronJackson/vrn)\n\nLarge Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression(3D Face Reconstruction from a Single Image)\n\n**[4] PRNet**   [**[paper]**](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yao_Feng_Joint_3D_Face_ECCV_2018_paper.pdf)     [**[github]**](https://github.com/YadiraF/PRNet)\n\nJoint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network\n\n**[5] 2DASL**      [**[paper]**](https://arxiv.org/abs/1903.09359)   [**[github]**](https://github.com/XgTu/2DASL)\n\nJoint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning \n\n#### Face attack \u0026 Defends\n\n[1] A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing\n\n[2] Deep Tree Learning for Zero-Shot Face Anti-Spoofing\n\n[3] Decorrelated Adversarial Learning for Age-Invariant Face Recognition\n\n[4] Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection\n\n[5] Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition\n\n##  ⚙️ Open source lib\n\n#### face recognition\n\n- [face.evoLVe.](https://github.com/ZhaoJ9014/face.evoLVe.PyTorch)\n- [face_recognition.pytorch](https://github.com/grib0ed0v/face_recognition.pytorch)\n-  [insightface](https://github.com/deepinsight/insightface )\n-  [face_recognition_framework](https://github.com/XiaohangZhan/face_recognition_framework)\n\n#### face detection\n\n- [libfaccedetection](https://github.com/ShiqiYu/libfacedetection)\n\n## 📦 Datasets\n\n#### 2D Face Recognition\n\n| Datasets                   | Description                                                  | Links                                                        | Publish Time |\n| -------------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------ |\n| **CASIA-WebFace**          | **10,575** subjects and **494,414** images                   | [Download](http://www.cbsr.ia.ac.cn/english/CASIA-WebFace-Database.html) | 2014         |\n| **MegaFace**🏅              | **1 million** faces, **690K** identities                     | [Download](http://megaface.cs.washington.edu/)               | 2016         |\n| **MS-Celeb-1M**🏅           | about **10M** images for **100K** celebrities   Concrete measurement to evaluate the performance of recognizing one million celebrities | [Download](http://www.msceleb.org)                           | 2016         |\n| **LFW**🏅                   | **13,000** images of faces collected from the web. Each face has been labeled with the name of the person pictured.  **1680** of the people pictured have two or more distinct photos in the data set. | [Download](http://vis-www.cs.umass.edu/lfw/)                 | 2007         |\n| **VGG Face2**🏅             | The dataset contains **3.31 million** images of **9131** subjects (identities), with an average of 362.6 images for each subject. | [Download](http://www.robots.ox.ac.uk/~vgg/data/vgg_face2/)  | 2017         |\n| **UMDFaces Dataset-image** | **367,888 face annotations** for **8,277 subjects.**         | [Download](http://www.umdfaces.io)                           | 2016         |\n| **Trillion Pairs**🏅        | Train: **MS-Celeb-1M-v1c** \u0026  **Asian-Celeb** Test: **ELFW\u0026DELFW** | [Download](http://trillionpairs.deepglint.com/overview)      | 2018         |\n| **FaceScrub**              | It comprises a total of **106,863** face images of male and female **530** celebrities, with about **200 images per person**. | [Download](http://vintage.winklerbros.net/facescrub.html)    | 2014         |\n| **Mut1ny**🏅                | head/face segmentation dataset contains over 17.3k labeled images | [Download](http://www.mut1ny.com/face-headsegmentation-dataset) | 2018         |\n| **IMDB-Face**              | The dataset contains about 1.7 million faces, 59k identities, which is manually cleaned from 2.0 million raw images. | [Download](https://github.com/fwang91/IMDb-Face)             | 2018         |\n| **DiF**                    | 'Diversity in Faces' Dataset to Advance Study of Fairness in Facial Recognition Systems | [Download](https://www.ibm.com/blogs/research/2019/01/diversity-in-faces/) | 2019         |\n| **Megaface2**              | Level Playing Field for Million Scale Face Recognition(**672K people in 4.7M images**) | [Download](http://megaface.cs.washington.edu/dataset/download_training.html) | 2019         |\n\n#### Video face recognition \n\n| Datasets                    | Description                                                  | Links                                                        | Publish Time |\n| --------------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------ |\n| **YouTube Face**🏅           | The data set contains **3,425** videos of **1,595** different people. | [Download](http://www.cs.tau.ac.il/%7Ewolf/ytfaces/)         | 2011         |\n| **UMDFaces Dataset-video**🏅 | Over **3.7 million** annotated video frames from over **22,000** videos of **3100 subjects.** | [Download](http://www.umdfaces.io)                           | 2017         |\n| **PaSC**                    | The challenge includes 9,376 still images and 2,802 videos of 293 people. | [Download](https://www.nist.gov/programs-projects/point-and-shoot-face-recognition-challenge-pasc) | 2013         |\n| **YTC**                     | The data consists of two parts: video clips (1910 sequences of 47 subjects) and initialization data(initial frame face bounding boxes, manually marked). | [Download](http://seqamlab.com/youtube-celebrities-face-tracking-and-recognition-dataset/) | 2008         |\n| **iQIYI-VID**🏅              | The iQIYI-VID dataset **contains 500,000 videos clips of 5,000 celebrities, adding up to 1000 hours**. This dataset supplies multi-modal cues, including face, cloth, voice, gait, and subtitles, for character identification. | [Download](http://challenge.ai.iqiyi.com/detail?raceId=5b1129e42a360316a898ff4f) | 2018         |\n\n#### 3D face recognition \n\n| Datasets       | Description                                                  | Links                                                        | Publish Time |\n| -------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------ |\n| **Bosphorus**🏅 | 105 subjects and 4666 faces 2D \u0026 3D face data                | [Download](http://bosphorus.ee.boun.edu.tr/default.aspx)     | 2008         |\n| **BD-3DFE**    | Analyzing **Facial Expressions** in **3D** Space             | [Download](http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html) | 2006         |\n| **ND-2006**    | 422 subjects and 9443 faces 3D Face Recognition              | [Download](https://sites.google.com/a/nd.edu/public-cvrl/data-sets) | 2006         |\n| **FRGC V2.0**  | 466 subjects and 4007 of 3D Face, Visible Face Images        | [Download](https://sites.google.com/a/nd.edu/public-cvrl/data-sets) | 2005         |\n| **B3D(AC)^2**  | **1000** high quality, dynamic **3D scans** of faces, recorded while pronouncing a set of English sentences. | [Download](http://www.vision.ee.ethz.ch/datasets/b3dac2.en.html) | 2010         |\n\n#### Anti-spoofing  \n\n| Datasets          | \\# of subj. / \\# of sess. | Links                                                        | Year | Spoof attacks attacks | Publish Time |\n| ----------------- | :-----------------------: | ------------------------------------------------------------ | ---- | --------------------- | ------------ |\n| **NUAA**          |           15/3            | [Download](http://parnec.nuaa.edu.cn/xtan/data/nuaaimposterdb.html) | 2010 | **Print**             | 2010         |\n| **CASIA-MFSD**    |           50/3            | Download(link failed)                                        | 2012 | **Print, Replay**     | 2012         |\n| **Replay-Attack** |           50/1            | [Download](https://www.idiap.ch/dataset/replayattack)        | 2012 | **Print, 2 Replay**   | 2012         |\n| **MSU-MFSD**      |           35/1            | [Download](https://www.cse.msu.edu/rgroups/biometrics/Publications/Databases/MSUMobileFaceSpoofing/index.htm) | 2015 | **Print, 2 Replay**   | 2015         |\n| **MSU-USSA**      |          1140/1           | [Download](http://biometrics.cse.msu.edu/Publications/Databases/MSU_USSA/) | 2016 | **2 Print, 6 Replay** | 2016         |\n| **Oulu-NPU**      |           55/3            | [Download](https://sites.google.com/site/oulunpudatabase/)   | 2017 | **2 Print, 6 Replay** | 2017         |\n| **Siw**           |           165/4           | [Download](http://cvlab.cse.msu.edu/spoof-in-the-wild-siw-face-anti-spoofing-database.html) | 2018 | **2 Print, 4 Replay** | 2018         |\n\n#### Cross age and cross pose\n\n| Datasets     | Description                                                  | Links                                                        | Publish Time |\n| ------------ | :----------------------------------------------------------- | ------------------------------------------------------------ | ------------ |\n| **CACD2000** | The dataset contains more than 160,000 images of 2,000 celebrities with **age ranging from 16 to 62**. | [Download](http://bcsiriuschen.github.io/CARC/)              | 2014         |\n| **FGNet**    | The dataset contains more than 1002 images of 82 people with **age ranging from 0 to 69**. | [Download](http://www-prima.inrialpes.fr/FGnet/html/benchmarks.html) | 2000         |\n| **MPRPH**    | The MORPH database contains **55,000** images of more than **13,000** people within the age ranges of **16** to **77** | [Download](http://www.faceaginggroup.com/morph/)             | 2016         |\n| **CPLFW**    | we construct a Cross-Pose LFW (CPLFW) which deliberately searches and selects **3,000 positive face pairs** with **pose difference** to add pose variation to intra-class variance. | [Download](http://www.whdeng.cn/cplfw/index.html)            | 2017         |\n| **CALFW**    | Thereby we construct a Cross-Age LFW (CALFW) which deliberately searches and selects **3,000 positive face pairs** with **age gaps** to add aging process intra-class variance. | [Download](http://www.whdeng.cn/calfw/index.html)            | 2017         |\n\n#### Face Detection\n\n| Datasets         | Description                                                  | Links                                                       | Publish Time |\n| ---------------- | ------------------------------------------------------------ | ----------------------------------------------------------- | ------------ |\n| **FDDB**🏅        | **5171** faces in a set of **2845** images                   | [Download](http://vis-www.cs.umass.edu/fddb/index.html)     | 2010         |\n| **Wider-face** 🏅 | **32,203** images and label **393,703** faces with a high degree of variability in scale, pose and occlusion, organized based on **61** event classes | [Download](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/) | 2015         |\n| **AFW**          | AFW dataset is built using Flickr images. It has **205** images with **473** labeled faces. For each face, annotations include a rectangular **bounding box**, **6 landmarks** and the **pose angles**. | [Download](http://www.ics.uci.edu/~xzhu/face/)              | 2013         |\n| **MALF**         | MALF is the first face detection dataset that supports fine-gained evaluation. MALF consists of **5,250** images and **11,931** faces. | [Download](http://www.cbsr.ia.ac.cn/faceevaluation/)        | 2015         |\n\n#### Face Attributes \n\n| Datasets                             | Description                                                  | Links                                                        | Key features                                 | Publish Time |\n| ------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | -------------------------------------------- | ------------ |\n| **CelebA**                           | **10,177** number of **identities**,  **202,599** number of **face images**, and  **5 landmark locations**, **40 binary attributes** annotations per image. | [Download](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) | **attribute \u0026 landmark**                     | 2015         |\n| **IMDB-WIKI**                        | 500k+ face images with **age** and **gender** labels         | [Download](https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/) | **age \u0026 gender**                             | 2015         |\n| **Adience**                          | Unfiltered faces for **gender** and **age** classification   | [Download](http://www.openu.ac.il/home/hassner/Adience/data.html) | **age \u0026 gender**                             | 2014         |\n| **WFLW**🏅                            | WFLW contains **10000 faces** (7500 for training and 2500 for testing) with **98 fully manual annotated landmarks**. | [Download](https://wywu.github.io/projects/LAB/WFLW.html)    | **landmarks**                                | 2018         |\n| **Caltech10k Web Faces**             | The dataset has 10,524 human faces of various resolutions and in **different settings** | [Download](http://www.vision.caltech.edu/Image_Datasets/Caltech_10K_WebFaces/#Description) | **landmarks**                                | 2005         |\n| **EmotioNet**                        | The EmotioNet database includes**950,000 images** with **annotated AUs**.  A **subset** of the images in the EmotioNet database correspond to **basic and compound emotions.** | [Download](http://cbcsl.ece.ohio-state.edu/EmotionNetChallenge/index.html#overview) | **AU and Emotion**                           | 2017         |\n| **RAF( Real-world Affective Faces)** | **29672** number of **real-world images**,  including **7** classes of basic emotions and **12** classes of compound emotions,  **5 accurate landmark locations**,  **37 automatic landmark locations**, **race, age range** and  **gender** **attributes** annotations per image | [Download](  \u003chttp://www.whdeng.cn/RAF/model1.html\u003e)         | **Emotions、landmark、race、age and gender** | 2017         |\n| **FairFace**                         | FairFace: Face Attribute Dataset for **Balanced Race**, **Gender**, and **Age** |                                                              | **balance race compoition**                  | 2019         |\n| **LS3D-W**                           | A large-scale 3D face alignment dataset constructed by annotating the images from AFLW, 300VW, 300W and FDDB in a consistent manner with 68 points using the automatic method | [Download](https://adrianbulat.com/face-alignment)           | **3D landmark**                              | 2017         |\n\n#### Others\n\n| Datasets           | Description                                                  | Links                                                        | Publish Time |\n| ------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------ |\n| **IJB C/B/A**🏅     | IJB C/B/A is currently running **three challenges** related to  **face detection, verification, identification, and identity clustering.** | [Download](https://www.nist.gov/programs-projects/face-challenges) | 2015         |\n| **MOBIO**          | **bi-modal** (**audio** and **video**) data taken from 152 people. | [Download](https://www.idiap.ch/dataset/mobio)               | 2012         |\n| **BANCA**          | The BANCA database was captured in four European languages in **two modalities** (**face** and **voice**). | [Download](http://www.ee.surrey.ac.uk/CVSSP/banca/)          | 2014         |\n| **3D Mask Attack** | **76500** frames of **17** persons using Kinect RGBD with eye positions (Sebastien Marcel). | [Download](https://www.idiap.ch/dataset/3dmad)               | 2013         |\n| **WebCaricature**  | **6042** **caricatures** and **5974 photographs** from **252 persons** collected from the web | [Download](https://cs.nju.edu.cn/rl/WebCaricature.htm)       | 2018         |\n\n## 🏠 Research home(conf \u0026 workshop \u0026 trans)\n\n![](./img/research_home.jpg)\n\n\n\n###### Conference\n\n**ICCV**: [IEEE International Conference on Computer Vision](http://iccv2019.thecvf.com)\n\n**CVPR**: [IEEE Conference on Computer Vision and Pattern Recognition](http://cvpr2018.thecvf.com/)\n\n**ECCV**: [European Conference on Computer Vision](https://eccv2018.org)\n\n**FG**: [IEEE International Conference on Automatic Face and Gesture Recognition](http://dblp.uni-trier.de/db/conf/fgr/)\n\n**BMVC:** [The British Machine Vision Conference](http://www.bmva.org/bmvc/?id=bmvc)\n\n**IJCB[ICB+BTAS]**:International Joint Conference on Biometrics\n\n- **ICB**: [International Conference on Biometrics](http://icb2018.org)\n\n- **BTAS**: [IEEE International Conference on Biometrics: Theory, Applications and Systems](\u003chttps://www.isi.edu/events/btas2018/home\u003e)\n\n**AMFG**: IEEE workshop on Analysis and Modeling of Faces and Gestures\n\n###### Workshop on Biometrics\n\n**TPAMI:** [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34)\n\n**IJCV:** [International Journal of Computer Vision](https://link.springer.com/journal/11263) \n\n**TIP:** [IEEE Transactions on Image Processing](https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83)\n\n**TIFS:** [IEEE Transactions on Information Forensics and Security](IEEE Transactions on Information Forensics and Security)\n\n**PR:** [Pattern Recognition](https://www.journals.elsevier.com/pattern-recognition/)\n\n## 🏷 References\n\n[1] \u003chttps://github.com/RiweiChen/DeepFace/tree/master/FaceDataset\u003e\n\n[2] \u003chttps://www.zhihu.com/question/33505655?sort=created\u003e\n\n[3] https://github.com/betars/Face-Resources\n\n[4] https://zhuanlan.zhihu.com/p/33288325\n\n[5] https://github.com/L706077/DNN-Face-Recognition-Papers\n\n[6] https://www.zhihu.com/question/67919300\n\n[7] https://jackietseng.github.io/conference_call_for_paper/2018-2019-conferences.html\n\n[8]http://history.ccf.org.cn/sites/ccf/biaodan.jsp?contentId=2903940690839\n\n[9]http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/WiderFace_Results.html\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FpolarisZhao%2Fawesome-face","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FpolarisZhao%2Fawesome-face","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FpolarisZhao%2Fawesome-face/lists"}